Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0001

Data Index: 1503712 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1422085 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9544. Min Act: -0.0001

Data Index: 1501444 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1652286 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1439001 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1629931 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1400544 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1599947 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1463645 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1638113 (Python Code)

Max Activating Token Index: 250

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8449. Min Act: -0.0001

Data Index: 1500232 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1479685 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8408. Min Act: -0.0001

Data Index: 1473081 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9811. Min Act: -0.0001

Data Index: 1421557 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1453468 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8315. Min Act: -0.0001

Data Index: 1546280 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7907. Min Act: -0.0001

Data Index: 1541004 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1558133 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8231. Min Act: -0.0001

Data Index: 1495749 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8237. Min Act: -0.0001

Data Index: 1507248 (Python Code)

Max Activating Token Index: 237